INDEX

Explanations

references to notable events and collaborations in science and media

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Followed by certain punctuation or "user"

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Distra

-0.35

unt

-0.35

 Christi

-0.34

 Initiate

-0.33

 diag

-0.32

 godly

-0.32

midt

-0.31

ent

-0.30

Cafe

-0.30

POSITIVE LOGITS

 Inscrivez

0.91

 particulières

0.75

 disambiguazione

0.75

 Formación

0.70

 fondament

0.69

 Contactez

0.68

 autorytatywna

0.67

 personnalisées

0.66

 Domínguez

0.66

 prevé

0.66

Activations Density 0.102%

references to notable events and collaborations in science and media

Followed by certain punctuation or "user"

No Comments

No Known Activations